Benjamin Reavill

LLM Algorithm Lead$200,000 - $300,000San Francisco, HybridFull-time / PermanentA product-focused AI start-up is building LLM systems that run in production and are used daily by over a million professionals. This role is responsible for designing, shipping, and maintaining applied LLM systems that support real product features, with an emphasis on reliability, cost, and scale rather than experimentation. Why This Role MattersOwn how LLM systems behave in a large, user-facing productMake architectural decisions that affect reliability, latency, and costMove LLM features from prototype to stable production systemsSet technical direction for applied LLM algorithms and evaluation practicesWhat You’ll DoDesign structured LLM workflows, including planning, reasoning, and multi-step executionBuild and maintain core components such as memory, personalization, and reusable LLM modulesLead development of LLM-powered product features from design through productionBuild and optimize retrieval pipelines (RAG) via chunking, indexing, reranking, and evaluationSelect and route between models based on performance, cost, and latency constraintsDefine evaluation metrics, monitoring, and feedback loopsDebug production issues and drive algorithm-level improvementsWhat You BringExperience shipping LLM-based systems into productionStrong understanding of prompting, reasoning workflows, and system designHands-on experience with RAG systemsExperience building evaluation, monitoring, or safety mechanismsAbility to lead technical decisions and guide other engineersExperience with inference optimization, efficiency, or large-scale systems is a plus

AI Applied Engineer$200,000 - $300,000San Francisco, HybridPermanent / Full-timeA product-led AI start-up is building one of the most widely adopted AI work companions in the world, operating at massive real-user scale with millions of professionals relying on it daily. The challenge problem now is designing AI systems that reliably support complex knowledge work across preparation, collaboration, and follow-through, inside products people trust. This role is ideal for someone who wants to work across AI engineering, product thinking, and ultimately shape how AI actually shows up in day-to-day professional workflows. Why This Role MattersOwn how AI supports high-stakes knowledge workDesign multi-step AI workflows that users rely on repeatedlyHelp define how agent-like systems behave inside a consumer-grade productWork beyond prompt design into evaluation, iteration, and reliabilityWhat You’ll DoOwn the end-to-end design of AI-first workflows for preparation, collaboration, and follow-up Design and iterate multi-step LLM / agentic systems, spanning intent understanding, planning, tool invocation, memory usage, and refinement loopsBuild reusable AI skills, prompts, templates, and evaluation pipelines that can power multiple product experiencesDefine success metrics for AI behaviour, run experiments, and use real interaction data to improve usefulness and reliabilityPartner closely with engineering and ML teams to ship quickly while maintaining a high bar for product quality and user experienceWhat You BringProven experience shipping AI/ML powered products end to endStrong working understanding of LLM systems: prompting, tool calling, retrieval, context construction, evaluation, and common failure modesAbility to translate user needs into clear flows, specs, and examples, including edge cases and expected behavioursComfort working directly with data and interaction logs to debug issues and compare variantsHands-on experience designing agent-like workflows involving multi-step plans, multiple tools, and refinement or self-correction

Agentic AI Engineer$200,000 - $300,000San Francisco, HybridPermanent / Full-timeA product-led AI start-up is building one of the most widely adopted AI work companions in the world, operating at massive real-user scale with millions of daily interactions. The challenge has shifted to designing agent systems that can plan, reason, evaluate themselves, and operate reliably inside real products. This is an opportunity to work from first principles on agentic architectures that power production systems used by professionals globally. Why This Role MattersBuild agent systems that plan, act, reflect, and improve across complex, ambiguous user workflowsDefine foundational patterns for LLM tool-use, reasoning graphs, and self-evaluation in productionJoin at a point where agent architecture decisions will shape the long-term platformWork on problems beyond prompt engineering like runtime reliability, context limits, and learning flywheelsWhat You’ll DoDesign and implement Plan–Act–Reflection style agent architecturesBuild DAG-based reasoning flows to deconstruct user intent into executable stepsDevelop agent skills including function calling, MCP-style integrations, and streaming APIsSolve runtime problems like context overflow / context rot through isolation, compression, and offloading strategiesArchitect automated evaluation and learning pipelines (reward functions, LLM-as-judge, RFT-style systems)What You BringProven experience building and shipping agentic AI systemsStrong understanding of workflow design, failure modes, and deterministic executionComfort designing distributed systems, APIs, and protocols used across teamsPractical experience with agent orchestration frameworks